Loading video...

Video Failed to Load

Go Home

These aquatic robots are more advanced than they look!๐Ÿฌ Early versions developed by Walt Disney Imagineering started as simple underwater drones, essentially radio-controlled machines, using jet pumps for propulsion and servo motors for control. Functional, but clearly nothing new. Then came the biomimetic stuff. Larger prototypes began mimicking dolphins,...

lukas_m_ziegler's profile picture

Lukas Ziegler

52,434 subscribers

67,279 views โ€ข 7 months ago โ€ขvia X (Twitter)

News & PoliticsEducationScience & Technology
LIVE

Anya Rossiโ€ข Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Robots with tentacles! ๐Ÿ™ SpiRobs are soft robots inspired by nature, designed in the shape of a logarithmic spiral. They mimic the flexible movements of octopus arms and elephant trunks to grasp objects. ๐Ÿ˜ SpiRobs use simple cables to move, making them easy to control and operate. They can scale from small to large sizes, ranging from centimeters to meters. The robots can adapt to different object shapes, improving their grasping ability. A mini version can act as a tiny gripper, while a large version can be mounted on drones. Interestingly, multiple robots can work together to wrap around and hold large objects. That's just out of this world! ๐Ÿ˜ฎโ€๐Ÿ’จ ~~ โ™ป๏ธ Join the weekly robotics newsletter, and never miss any news โ†’
1:04

Robots with tentacles! ๐Ÿ™ SpiRobs are soft robots inspired by nature, designed in the shape of a logarithmic spiral. They mimic the flexible movements of octopus arms and elephant trunks to grasp objects. ๐Ÿ˜ SpiRobs use simple cables to move, making them easy to control and operate. They can scale from small to large sizes, ranging from centimeters to meters. The robots can adapt to different object shapes, improving their grasping ability. A mini version can act as a tiny gripper, while a large version can be mounted on drones. Interestingly, multiple robots can work together to wrap around and hold large objects. That's just out of this world! ๐Ÿ˜ฎโ€๐Ÿ’จ ~~ โ™ป๏ธ Join the weekly robotics newsletter, and never miss any news โ†’

Lukas Ziegler

121,345 views โ€ข 7 months ago

Robots might learn better from video than from language! ๐Ÿ“ผ Most Vision-Language-Action (VLA) models learn what to do from text, but still struggle with how things move in the real world. That makes them data-hungry and slow to train. mimic video takes a different route. Instead of grounding robot control in text, it grounds it in video, using large pre-trained video models that already capture physical motion and dynamics. The idea is straightforward: let the video model handle โ€œwhat will happen next,โ€ and let a smaller control model focus only on turning that visual plan into robot actions. The result is big gains in practice. Robots trained this way need 10ร— less data, converge twice as fast, and perform better on both simulated benchmarks and real bimanual manipulation tasks. If robots can โ€œimagineโ€ motion using video, control becomes a much simpler problem. Shoutout to Jonas Pai, Liam Achenbach, Oier Mees, Elvis Nava and the rest of the team! Here's the project page: ~~ โ™ป๏ธ Join the weekly robotics newsletter, and never miss any news โ†’
0:47

Robots might learn better from video than from language! ๐Ÿ“ผ Most Vision-Language-Action (VLA) models learn what to do from text, but still struggle with how things move in the real world. That makes them data-hungry and slow to train. mimic video takes a different route. Instead of grounding robot control in text, it grounds it in video, using large pre-trained video models that already capture physical motion and dynamics. The idea is straightforward: let the video model handle โ€œwhat will happen next,โ€ and let a smaller control model focus only on turning that visual plan into robot actions. The result is big gains in practice. Robots trained this way need 10ร— less data, converge twice as fast, and perform better on both simulated benchmarks and real bimanual manipulation tasks. If robots can โ€œimagineโ€ motion using video, control becomes a much simpler problem. Shoutout to Jonas Pai, Liam Achenbach, Oier Mees, Elvis Nava and the rest of the team! Here's the project page: ~~ โ™ป๏ธ Join the weekly robotics newsletter, and never miss any news โ†’

Lukas Ziegler

50,063 views โ€ข 7 months ago

Magnetic levitation for surgical robots! ๐Ÿงฒ A research team working on minimally invasive surgery just introduced a remote magnetic levitation to move things inside our bodies. Their main goal is to control guidewires and catheters inside the body using magnetic fields. But levitation is unstable and extreme, it forces them to solve fundamental control problems they can't avoid. They have to handle strong magnetic field nonlinearities, develop real-time invertible models, and create control methods that work on any eMNS (electroMagnetic Navigation System) and any object. The real challenge is the position and orientation feedback. You can control a magnet outside the body, but once a catheter or drug-delivery robot is inside a patient, you can't see it. There's no vision, but just magnetic fields and current measurements. That's huge news coming out of ETH Zurich! Here's the paper: Mentioned all authors on Li, but coulnd't find them here! ~~ โ™ป๏ธ Join the weekly robotics newsletter, and never miss any news โ†’
0:20

Magnetic levitation for surgical robots! ๐Ÿงฒ A research team working on minimally invasive surgery just introduced a remote magnetic levitation to move things inside our bodies. Their main goal is to control guidewires and catheters inside the body using magnetic fields. But levitation is unstable and extreme, it forces them to solve fundamental control problems they can't avoid. They have to handle strong magnetic field nonlinearities, develop real-time invertible models, and create control methods that work on any eMNS (electroMagnetic Navigation System) and any object. The real challenge is the position and orientation feedback. You can control a magnet outside the body, but once a catheter or drug-delivery robot is inside a patient, you can't see it. There's no vision, but just magnetic fields and current measurements. That's huge news coming out of ETH Zurich! Here's the paper: Mentioned all authors on Li, but coulnd't find them here! ~~ โ™ป๏ธ Join the weekly robotics newsletter, and never miss any news โ†’

Lukas Ziegler

120,803 views โ€ข 1 month ago

Octopus inspired robot! ๐Ÿ™ Researchers at the National University of Singapore have created a streamlined octopus-inspired swimming robot capable of replicating the animalโ€™s agile movement through water. Unlike previous designs that require eight actuators for each arm, this robot simplifies the mechanics using just two motors and an umbrella-like mechanism to coordinate its eight soft arms. As it swims, the robotโ€™s arms gently open to reduce drag, then quickly close to generate thrust mimicking the jet-propulsion used by real octopuses. In lab tests, it reached speeds up to 314 mm/s. This soft robotic platform not only matches the swimming performance of more complex systems but also offers greater energy efficiency. Pretty cool nature-inspired robot application! ๐Ÿ‘€ ~~ โ™ป๏ธ Join the weekly robotics newsletter, and never miss any news โ†’
0:42

Octopus inspired robot! ๐Ÿ™ Researchers at the National University of Singapore have created a streamlined octopus-inspired swimming robot capable of replicating the animalโ€™s agile movement through water. Unlike previous designs that require eight actuators for each arm, this robot simplifies the mechanics using just two motors and an umbrella-like mechanism to coordinate its eight soft arms. As it swims, the robotโ€™s arms gently open to reduce drag, then quickly close to generate thrust mimicking the jet-propulsion used by real octopuses. In lab tests, it reached speeds up to 314 mm/s. This soft robotic platform not only matches the swimming performance of more complex systems but also offers greater energy efficiency. Pretty cool nature-inspired robot application! ๐Ÿ‘€ ~~ โ™ป๏ธ Join the weekly robotics newsletter, and never miss any news โ†’

Lukas Ziegler

16,161 views โ€ข 7 days ago

Robots moving railcars! ๐Ÿšƒ Did you know that KUKA is also in the mobile robots business? Yes, you heard that right. And not just any robots. Robots that carry up to 56 tons! ๐Ÿ‹๐Ÿผ The railcar production process is highly complex, particularly when moving massive cars sideways within a plant. This challenge has been addressed at the Siemens facility in Germany using the OmniMove system from KUKA. The system allows for precise positioning, enabling the units to lift, move, and lower railcars with remarkable accuracy. With Mecanum wheels, the OmniMove units can move seamlessly in any direction, making the process incredibly efficient. Together, these units are capable of lifting up to 56 tons, streamlining heavy railcar production. This one is clearly tele-operated, but just looking at it makes me feel safer when I see a human in the loop. What a great use case for mobile robots! ๐Ÿ˜ฎโ€๐Ÿ’จ ~~ โ™ป๏ธ Join the weekly robotics newsletter, and never miss any news โ†’
0:38

Robots moving railcars! ๐Ÿšƒ Did you know that KUKA is also in the mobile robots business? Yes, you heard that right. And not just any robots. Robots that carry up to 56 tons! ๐Ÿ‹๐Ÿผ The railcar production process is highly complex, particularly when moving massive cars sideways within a plant. This challenge has been addressed at the Siemens facility in Germany using the OmniMove system from KUKA. The system allows for precise positioning, enabling the units to lift, move, and lower railcars with remarkable accuracy. With Mecanum wheels, the OmniMove units can move seamlessly in any direction, making the process incredibly efficient. Together, these units are capable of lifting up to 56 tons, streamlining heavy railcar production. This one is clearly tele-operated, but just looking at it makes me feel safer when I see a human in the loop. What a great use case for mobile robots! ๐Ÿ˜ฎโ€๐Ÿ’จ ~~ โ™ป๏ธ Join the weekly robotics newsletter, and never miss any news โ†’

Lukas Ziegler

19,148 views โ€ข 1 month ago

HUGE FUNDING JUMP FOR AUTONOMOUS KILLER ROBOTS BREAKING NEWS: The Pentagon this week filed a call for a 24,000% cash increase (not a misprint) for a unit that creates flying killer robots for use in a war on China. Many of the machines will be able to attack autonomously, rather than being remote controlled. The step was revealed in a request filed this week, for US$55bn to fund a new unit called the Defense Autonomous Warfare Group. This is โ€œthe largest single commitment to autonomous warfare in history. Its scale should be applauded,โ€ said former CIA director David Petraeus. . PLANNED WAR ON CHINA The DAWG is a new Pentagon department, built on top of a Joe Biden initiative to create drones for use on a planned war on China. The funding demand is so large because the US last December banned the purchase of drones and components from China, the world leader in that area. It would be problematic to ask the Chinese to continue to provide equipment for the US to use to attack China. The undersecretary for war, Elbridge Colby, has long called for a US war on China, exploiting Taiwan as justification. . WHICH NATIONS BACK KILLER ROBOTS? The Pentagon has long been using the argument that they are responding to Chinaโ€™s use of killer robots, although this appears to be untrue. In 2019, China and the majority of other countries of the world met at the UN to back a motion which said that the granting of power to machines to kill humans was a horrific idea which should be banned globally. But four known militaristic nations were among those which disagreed with the motion: The US, the UK, Russia and Australia. . SCIENTIST'S WARNING In January this year, one of the worldโ€™s top scientists, physicist Max Tegmark, said technologists opposing killer robots programs should be commended โ€œfor standing up for the principle that AI should never be used to kill people without meaningful human controlโ€. However, that assumes that ethical human-centered thinking will be at the center of decisionsโ€”and that is clearly not the case. Military power, global dominance and profit are the ruling motivations. . TRUMP'S ELDEST SONS The Pentagon wants private company participation and is getting it. A top US dronemaker called Powerus is already offering autonomous US drones to Gulf nations. The Arab nations allowed the US and Israel to launch attacks on Iran from their countries and now have to deal with the Iranians defending themselves. Powerus, which has Donald Trumpโ€™s two oldest sons on its board, cannot lose. Trump senior has launched an unprovoked attack on Iran from the Gulf nations, and the younger Trumps are now involved with a firm selling autonomous drones for protection. All this, sadly, mitigates against hopes for peace.
2:36

HUGE FUNDING JUMP FOR AUTONOMOUS KILLER ROBOTS BREAKING NEWS: The Pentagon this week filed a call for a 24,000% cash increase (not a misprint) for a unit that creates flying killer robots for use in a war on China. Many of the machines will be able to attack autonomously, rather than being remote controlled. The step was revealed in a request filed this week, for US$55bn to fund a new unit called the Defense Autonomous Warfare Group. This is โ€œthe largest single commitment to autonomous warfare in history. Its scale should be applauded,โ€ said former CIA director David Petraeus. . PLANNED WAR ON CHINA The DAWG is a new Pentagon department, built on top of a Joe Biden initiative to create drones for use on a planned war on China. The funding demand is so large because the US last December banned the purchase of drones and components from China, the world leader in that area. It would be problematic to ask the Chinese to continue to provide equipment for the US to use to attack China. The undersecretary for war, Elbridge Colby, has long called for a US war on China, exploiting Taiwan as justification. . WHICH NATIONS BACK KILLER ROBOTS? The Pentagon has long been using the argument that they are responding to Chinaโ€™s use of killer robots, although this appears to be untrue. In 2019, China and the majority of other countries of the world met at the UN to back a motion which said that the granting of power to machines to kill humans was a horrific idea which should be banned globally. But four known militaristic nations were among those which disagreed with the motion: The US, the UK, Russia and Australia. . SCIENTIST'S WARNING In January this year, one of the worldโ€™s top scientists, physicist Max Tegmark, said technologists opposing killer robots programs should be commended โ€œfor standing up for the principle that AI should never be used to kill people without meaningful human controlโ€. However, that assumes that ethical human-centered thinking will be at the center of decisionsโ€”and that is clearly not the case. Military power, global dominance and profit are the ruling motivations. . TRUMP'S ELDEST SONS The Pentagon wants private company participation and is getting it. A top US dronemaker called Powerus is already offering autonomous US drones to Gulf nations. The Arab nations allowed the US and Israel to launch attacks on Iran from their countries and now have to deal with the Iranians defending themselves. Powerus, which has Donald Trumpโ€™s two oldest sons on its board, cannot lose. Trump senior has launched an unprovoked attack on Iran from the Gulf nations, and the younger Trumps are now involved with a firm selling autonomous drones for protection. All this, sadly, mitigates against hopes for peace.

Nury Vittachi

13,872 views โ€ข 3 months ago

Something must change in robotics! ๐Ÿ˜– As more billion-dollar players enter the space, more systems are closing off. APIs move behind paywalls, platforms lock down, and robots turn into black boxes. Pollen Robotics is taking the opposite route. With Reachy 2, everything is open: the code, the CAD files, the ROS 2 interfaces, the communication stack. If you want to swap the camera, redesign the gripper, or fork the whole system, you can, and thatโ€™s the point. It creates a culture where universities can run real experiments without licensing drama, and startups can prototype without waiting for vendor permission. Clone it on GitHub. Add behaviors. Share datasets. Fork the models. Push improvements upstream. The Hugging Face influence is real. Itโ€™s two open ecosystems aligning around the same idea: robotics should be built by more than a handful of companies. It was so cool to meet the team behind Reachy 2 in Bordeaux! ๐Ÿ”ฅ ~~ โ™ป๏ธ Join the weekly robotics newsletter, and never miss any news โ†’
1:16

Something must change in robotics! ๐Ÿ˜– As more billion-dollar players enter the space, more systems are closing off. APIs move behind paywalls, platforms lock down, and robots turn into black boxes. Pollen Robotics is taking the opposite route. With Reachy 2, everything is open: the code, the CAD files, the ROS 2 interfaces, the communication stack. If you want to swap the camera, redesign the gripper, or fork the whole system, you can, and thatโ€™s the point. It creates a culture where universities can run real experiments without licensing drama, and startups can prototype without waiting for vendor permission. Clone it on GitHub. Add behaviors. Share datasets. Fork the models. Push improvements upstream. The Hugging Face influence is real. Itโ€™s two open ecosystems aligning around the same idea: robotics should be built by more than a handful of companies. It was so cool to meet the team behind Reachy 2 in Bordeaux! ๐Ÿ”ฅ ~~ โ™ป๏ธ Join the weekly robotics newsletter, and never miss any news โ†’

Lukas Ziegler

21,046 views โ€ข 8 months ago

Thereโ€™s not enough hype about Flexion Robotics. They are literally one of the sexiest European companies these days! ๐Ÿ‡ช๐Ÿ‡บ I had a chance to meet the founder Nikita last year and learn his story. He turned down offers from top physical AI companies to build his own. The reason was his specific vision of how robot intelligence should be built to actually scale. So he decided to build one himself. Flexion is building an ultimate brain for humanoid robots. Yesterday they released Reflect v1.0. Itโ€™s an intelligence platform for long-horizon autonomous missions. The system has three layers. At the top, a custom vision-language model acts as mission control, observing the robot's camera feed and replanning continuously. Below that, a motion layer combines a VLA trained on real-world data with reinforcement learning-based skills. It translates perception into navigation, scene interaction, and manipulation commands. At the bottom, a whole-body controller runs in real-time, maintaining balance while the robot navigates and performs tasks. I highly recommend them visiting Zurich! ๐Ÿ‡จ๐Ÿ‡ญ Nikita Rudin cheapeu bas on the launch! ๐ŸŽฉ ~~ โ™ป๏ธ Join the weekly robotics newsletter, and never miss any news โ†’ http://
0:23

Thereโ€™s not enough hype about Flexion Robotics. They are literally one of the sexiest European companies these days! ๐Ÿ‡ช๐Ÿ‡บ I had a chance to meet the founder Nikita last year and learn his story. He turned down offers from top physical AI companies to build his own. The reason was his specific vision of how robot intelligence should be built to actually scale. So he decided to build one himself. Flexion is building an ultimate brain for humanoid robots. Yesterday they released Reflect v1.0. Itโ€™s an intelligence platform for long-horizon autonomous missions. The system has three layers. At the top, a custom vision-language model acts as mission control, observing the robot's camera feed and replanning continuously. Below that, a motion layer combines a VLA trained on real-world data with reinforcement learning-based skills. It translates perception into navigation, scene interaction, and manipulation commands. At the bottom, a whole-body controller runs in real-time, maintaining balance while the robot navigates and performs tasks. I highly recommend them visiting Zurich! ๐Ÿ‡จ๐Ÿ‡ญ Nikita Rudin cheapeu bas on the launch! ๐ŸŽฉ ~~ โ™ป๏ธ Join the weekly robotics newsletter, and never miss any news โ†’ http://

Lukas Ziegler

23,140 views โ€ข 1 month ago

๐Ÿ”ฅ JUST IN: Open-source robotics dataset from 100% real-world scenarios! ๐Ÿคฏ Chinese robotics company AGIBOT just released AGIBOT WORLD 2026, an open-source dataset systematically covering key embodied AI research directions. Built entirely from real-world environments: commercial spaces, and homes. Collected using AGIBOT G2 robots in free-form collection mode, providing structured, accurately annotated, high-quality data. Digital twin technology creates 1:1 scale replicas in simulation matching the real environments. Both real-world and simulation data are open-sourced. The AGIBOT G2 platform collects multiple data types simultaneously: RGB(D) cameras, tactile sensors, force sensors, LiDAR, IMU, and full-body joint states. Whole-body control coordinates arms, waist, and hands for complex tasks. First-person teleoperation lets operators control the robot from its perspective. The tasks covered are fine-grained manipulation, ultra-long-horizon tasks, spatial navigation, dual-arm coordination, and multi-agent/human-robot collaboration. The dataset includes error-recovery trajectories with annotations. Most datasets only show successful demonstrations. AGIBOT includes failures and how the robot recovers, teaching models how to handle mistakes. After collection, data is tested through policy training and real-robot deployment to ensure quality. Then processed through industrial quality control with multiple screening and cleaning rounds. Making it open-source accelerates embodied AI research by giving researchers access to high-quality real-world robot data at scale. ๐Ÿ‡จ๐Ÿ‡ณ Learn more here: ~~ โ™ป๏ธ Join the weekly robotics newsletter, and never miss any news โ†’
0:26

๐Ÿ”ฅ JUST IN: Open-source robotics dataset from 100% real-world scenarios! ๐Ÿคฏ Chinese robotics company AGIBOT just released AGIBOT WORLD 2026, an open-source dataset systematically covering key embodied AI research directions. Built entirely from real-world environments: commercial spaces, and homes. Collected using AGIBOT G2 robots in free-form collection mode, providing structured, accurately annotated, high-quality data. Digital twin technology creates 1:1 scale replicas in simulation matching the real environments. Both real-world and simulation data are open-sourced. The AGIBOT G2 platform collects multiple data types simultaneously: RGB(D) cameras, tactile sensors, force sensors, LiDAR, IMU, and full-body joint states. Whole-body control coordinates arms, waist, and hands for complex tasks. First-person teleoperation lets operators control the robot from its perspective. The tasks covered are fine-grained manipulation, ultra-long-horizon tasks, spatial navigation, dual-arm coordination, and multi-agent/human-robot collaboration. The dataset includes error-recovery trajectories with annotations. Most datasets only show successful demonstrations. AGIBOT includes failures and how the robot recovers, teaching models how to handle mistakes. After collection, data is tested through policy training and real-robot deployment to ensure quality. Then processed through industrial quality control with multiple screening and cleaning rounds. Making it open-source accelerates embodied AI research by giving researchers access to high-quality real-world robot data at scale. ๐Ÿ‡จ๐Ÿ‡ณ Learn more here: ~~ โ™ป๏ธ Join the weekly robotics newsletter, and never miss any news โ†’

Lukas Ziegler

40,583 views โ€ข 4 months ago

๐Ÿšจ BREAKING: Microsoft's first robotics foundation model! ๐Ÿคฏ Microsoft just announced Rho-alpha (ฯฮฑ), their first robotics model derived from the Phi series of vision-language models. Rho-alpha translates natural language commands into control signals for robotic systems performing bimanual manipulation tasks. Commands like "push the green button with the right gripper," "pull out the red wire," "flip the top switch on," or "turn the knob to position 5" get executed directly by dual-arm robots. What makes this different from standard vision-language-action (VLA) models is the additional modalities. Rho-alpha is a VLA+ model that adds tactile sensing to the perceptual mix, with plans to incorporate force feedback. On the learning side, the model is designed to continually improve during deployment by learning from human feedback. The training approach combines trajectories from physical demonstrations and simulated tasks with web-scale visual question answering data. Since teleoperation data is scarce and expensive, Microsoft is using NVIDIA Isaac Sim on Azure to generate physically accurate synthetic datasets via reinforcement learning. These simulated trajectories get combined with commercial and open physical demonstration datasets. The model is currently under evaluation on dual-arm setups and humanoid robots. Microsoft is opening an Early Access Program for organizations interested in evaluating Rho-alpha. Robots that can adapt to dynamic situations and human preferences are more useful in real environments and more trusted by the people operating them. Read more here: ~~ โ™ป๏ธ Join the weekly robotics newsletter, and never miss any news โ†’
0:34

๐Ÿšจ BREAKING: Microsoft's first robotics foundation model! ๐Ÿคฏ Microsoft just announced Rho-alpha (ฯฮฑ), their first robotics model derived from the Phi series of vision-language models. Rho-alpha translates natural language commands into control signals for robotic systems performing bimanual manipulation tasks. Commands like "push the green button with the right gripper," "pull out the red wire," "flip the top switch on," or "turn the knob to position 5" get executed directly by dual-arm robots. What makes this different from standard vision-language-action (VLA) models is the additional modalities. Rho-alpha is a VLA+ model that adds tactile sensing to the perceptual mix, with plans to incorporate force feedback. On the learning side, the model is designed to continually improve during deployment by learning from human feedback. The training approach combines trajectories from physical demonstrations and simulated tasks with web-scale visual question answering data. Since teleoperation data is scarce and expensive, Microsoft is using NVIDIA Isaac Sim on Azure to generate physically accurate synthetic datasets via reinforcement learning. These simulated trajectories get combined with commercial and open physical demonstration datasets. The model is currently under evaluation on dual-arm setups and humanoid robots. Microsoft is opening an Early Access Program for organizations interested in evaluating Rho-alpha. Robots that can adapt to dynamic situations and human preferences are more useful in real environments and more trusted by the people operating them. Read more here: ~~ โ™ป๏ธ Join the weekly robotics newsletter, and never miss any news โ†’

Lukas Ziegler

60,928 views โ€ข 6 months ago

Japan Just Built a HouseBot You Control Without Speaking and It Changes Everything! Donut Robotics has officially unveiled its first bipedal humanoid, Cinnamon 1, and instead of focusing on louder voices or bigger motors, the company went in the opposite direction. Silence. Cinnamon 1 introduces what Donut Robotics calls Silent Gesture Control, a system that allows the humanoid to be guided using simple hand and finger movements rather than spoken commands. This approach feels especially well suited for real world environments where traditional voice control falls apart. Busy factory floors. Construction sites filled with constant noise. Even quiet indoor settings where voice commands feel awkward or intrusive. It also opens the door for far more accessible human robot interaction, particularly for users with impairments. While the current Cinnamon 1 hardware is built on an OEM platform, the intelligence driving it is where Donut Robotics is placing its long term bet. The team is actively developing custom Vision Language Action AI that allows the robot to interpret what it sees, understand intent, and respond with physical action. The goal is not just smarter robots, but robots that feel more natural. Even more ambitious is the companyโ€™s plan for full domestic production. Donut Robotics has stated its intention to localize both manufacturing and AI development in Japan, reinforcing the countryโ€™s reputation for precision engineering and thoughtful robotics design. If timelines hold, Cinnamon 1 units are expected to begin deployment in factories and construction environments by the end of 2026. That puts this humanoid squarely in the category of near term reality rather than distant concept. The takeaway is simple but important. As humanoid robots move out of labs and into daily work environments, the winners may not be the loudest or flashiest machines. They may be the ones that understand us without a word being spoken.
0:31

Japan Just Built a HouseBot You Control Without Speaking and It Changes Everything! Donut Robotics has officially unveiled its first bipedal humanoid, Cinnamon 1, and instead of focusing on louder voices or bigger motors, the company went in the opposite direction. Silence. Cinnamon 1 introduces what Donut Robotics calls Silent Gesture Control, a system that allows the humanoid to be guided using simple hand and finger movements rather than spoken commands. This approach feels especially well suited for real world environments where traditional voice control falls apart. Busy factory floors. Construction sites filled with constant noise. Even quiet indoor settings where voice commands feel awkward or intrusive. It also opens the door for far more accessible human robot interaction, particularly for users with impairments. While the current Cinnamon 1 hardware is built on an OEM platform, the intelligence driving it is where Donut Robotics is placing its long term bet. The team is actively developing custom Vision Language Action AI that allows the robot to interpret what it sees, understand intent, and respond with physical action. The goal is not just smarter robots, but robots that feel more natural. Even more ambitious is the companyโ€™s plan for full domestic production. Donut Robotics has stated its intention to localize both manufacturing and AI development in Japan, reinforcing the countryโ€™s reputation for precision engineering and thoughtful robotics design. If timelines hold, Cinnamon 1 units are expected to begin deployment in factories and construction environments by the end of 2026. That puts this humanoid squarely in the category of near term reality rather than distant concept. The takeaway is simple but important. As humanoid robots move out of labs and into daily work environments, the winners may not be the loudest or flashiest machines. They may be the ones that understand us without a word being spoken.

The AI Robot Guy on X

257,928 views โ€ข 6 months ago

๐Ÿšจ BREAKING: ABB Robotics + NVIDIA close the sim-to-real gap with 99% accuracy! ๐Ÿ‘พ ABB Robotics is integrating NVIDIA Omniverse libraries into RobotStudio to deliver physical AI for industry, closing the gap from virtual training to real-world deployment with up to 99% accuracy. RobotStudio HyperReality, available second half of 2026, will fundamentally change how quickly manufacturers can scale production: reducing costs by up to 40%, accelerating time-to-market by 50%, and cutting setup and commissioning times by up to 80%. For decades, the deficit between simulation accuracy and real-world lighting, materials, and environments has limited manufacturers' ability to design advanced manufacturing processes in the virtual world. The only robot manufacturer with a virtual controller running the same firmware as the hardware, ensuring near-perfect correlation between simulation and real-world performance. The system uses physically accurate simulations and foundation models endlessly optimized with real-world data feedback. These models can train any number of ABB robots anywhere in the world with industrial-grade reliability. Foxconn is using RobotStudio HyperReality for consumer electronics assembly. Assembly robots are trained virtually using synthetic data to perfect multiple production processes across various scenarios, then moved to production lines with 99% accuracy. This eliminates physical training and tests, reducing setup times and costs. Workr is demonstrating AI-powered robotic systems at NVIDIA GTC 2026. Built on ABB technology, trained with synthetic data using NVIDIA Omniverse, deployed without operators needing programming knowledge . ๐Ÿšจ Iโ€™ll be onsite in San Jose during GTC 2026, and will be showing all the cool stuff that ABB Robotics prepared this year! Canโ€™t wait! ๐Ÿซก ~~ โ™ป๏ธ Join the weekly robotics newsletter, and never miss any news โ†’
0:48

๐Ÿšจ BREAKING: ABB Robotics + NVIDIA close the sim-to-real gap with 99% accuracy! ๐Ÿ‘พ ABB Robotics is integrating NVIDIA Omniverse libraries into RobotStudio to deliver physical AI for industry, closing the gap from virtual training to real-world deployment with up to 99% accuracy. RobotStudio HyperReality, available second half of 2026, will fundamentally change how quickly manufacturers can scale production: reducing costs by up to 40%, accelerating time-to-market by 50%, and cutting setup and commissioning times by up to 80%. For decades, the deficit between simulation accuracy and real-world lighting, materials, and environments has limited manufacturers' ability to design advanced manufacturing processes in the virtual world. The only robot manufacturer with a virtual controller running the same firmware as the hardware, ensuring near-perfect correlation between simulation and real-world performance. The system uses physically accurate simulations and foundation models endlessly optimized with real-world data feedback. These models can train any number of ABB robots anywhere in the world with industrial-grade reliability. Foxconn is using RobotStudio HyperReality for consumer electronics assembly. Assembly robots are trained virtually using synthetic data to perfect multiple production processes across various scenarios, then moved to production lines with 99% accuracy. This eliminates physical training and tests, reducing setup times and costs. Workr is demonstrating AI-powered robotic systems at NVIDIA GTC 2026. Built on ABB technology, trained with synthetic data using NVIDIA Omniverse, deployed without operators needing programming knowledge . ๐Ÿšจ Iโ€™ll be onsite in San Jose during GTC 2026, and will be showing all the cool stuff that ABB Robotics prepared this year! Canโ€™t wait! ๐Ÿซก ~~ โ™ป๏ธ Join the weekly robotics newsletter, and never miss any news โ†’

Lukas Ziegler

22,482 views โ€ข 5 months ago

This is the Scorpion Hexapod, a six-legged robotic scorpion created at Ghent University UGent Campus Kortrijk in Belgium. It was built by students Stephan Flamand Robbe Terryn and Pieterjan Deconinck as part of an Embedded Prototyping / Mechatronics Design project. What it is โ€ข A biomimetic robot inspired by the body and movement of a real scorpion โ€ข A hexapod, meaning it walks on six legs โ€ข A university prototype, not a commercial robot โ€ข Built to test animal-inspired movement, sensors and interactive behavior โ€ข Designed more for robotics research and education than real-world work Main hardware โ€ข 6 walking legs for crawling movement โ€ข 2 front claws for the scorpion look โ€ข Moving tail with a stinger-style mechanism โ€ข Sensors in the body, legs and claws โ€ข Arduino-based electronics for control โ€ข Front camera and proximity sensing โ€ข Battery pack for mobile operation โ€ข 3D-printed modules for legs and tail โ€ข Laser-cut ABS body parts โ€ข Thermoformed shell for the white outer body What it can do โ€ข Walk across the floor using its six legs โ€ข Move its tail like a real scorpion โ€ข React when a person gets close โ€ข Detect when someone covers its front sensors โ€ข Strike with its tail in the demo โ€ข Leave a red mark using a marker pen attached to the stinger โ€ข Operate through remote control โ€ข Perform some simple autonomous reactions Why it was created โ€ข To explore bio-inspired robotics โ€ข To show how digital fabrication can produce complex moving robots โ€ข To combine 3D printing, laser cutting, Arduino electronics and sensors โ€ข To teach students how to design a complete mechatronic system โ€ข To improve on an older robotic ant project that had weak autonomy, short battery life and motor problems โ€ข To create an interactive robot that reacts to humans in a visible way Important note โ€ข It was not built for combat โ€ข It was not made for industrial deployment โ€ข It is not a military robot โ€ข It is an educational robotics prototype made to demonstrate movement, sensing and interaction
0:30

This is the Scorpion Hexapod, a six-legged robotic scorpion created at Ghent University UGent Campus Kortrijk in Belgium. It was built by students Stephan Flamand Robbe Terryn and Pieterjan Deconinck as part of an Embedded Prototyping / Mechatronics Design project. What it is โ€ข A biomimetic robot inspired by the body and movement of a real scorpion โ€ข A hexapod, meaning it walks on six legs โ€ข A university prototype, not a commercial robot โ€ข Built to test animal-inspired movement, sensors and interactive behavior โ€ข Designed more for robotics research and education than real-world work Main hardware โ€ข 6 walking legs for crawling movement โ€ข 2 front claws for the scorpion look โ€ข Moving tail with a stinger-style mechanism โ€ข Sensors in the body, legs and claws โ€ข Arduino-based electronics for control โ€ข Front camera and proximity sensing โ€ข Battery pack for mobile operation โ€ข 3D-printed modules for legs and tail โ€ข Laser-cut ABS body parts โ€ข Thermoformed shell for the white outer body What it can do โ€ข Walk across the floor using its six legs โ€ข Move its tail like a real scorpion โ€ข React when a person gets close โ€ข Detect when someone covers its front sensors โ€ข Strike with its tail in the demo โ€ข Leave a red mark using a marker pen attached to the stinger โ€ข Operate through remote control โ€ข Perform some simple autonomous reactions Why it was created โ€ข To explore bio-inspired robotics โ€ข To show how digital fabrication can produce complex moving robots โ€ข To combine 3D printing, laser cutting, Arduino electronics and sensors โ€ข To teach students how to design a complete mechatronic system โ€ข To improve on an older robotic ant project that had weak autonomy, short battery life and motor problems โ€ข To create an interactive robot that reacts to humans in a visible way Important note โ€ข It was not built for combat โ€ข It was not made for industrial deployment โ€ข It is not a military robot โ€ข It is an educational robotics prototype made to demonstrate movement, sensing and interaction

Techniahqrobot | humanoid robots

28,079 views โ€ข 1 month ago

China unveils humanoid robot with lifelike skin and blinking eyes built for daily life | Prabhat Ranjan Mishra, Interesting Engineering Large Language Models (LLMs) and Vision-Language Models (VLMs) help process and interpret complex data from human interactions. A Shanghai-based company has developed humanoid robots that appear as real as humans. The advanced bionic humanoid robot is integrated with self-supervised AI algorithms. Named Elf V1, the robot can perceive the world, communicate, learn, and interact intelligently with its surroundings. Developed by AheadForm Technology, the robot offers up to 30 degrees of freedom, powered by a precise control system and an advanced AI learning algorithm. Robot offers expressive facial features The robot offers expressive facial features, moving eyes, and synchronized speech. It can also convey emotions and understand human non-verbal cues, making interactions more natural and engaging. The robot has highly interactive capabilities and lifelike appearances. AheadForm expects that its robots could soon seamlessly integrate into daily life, providing assistance, companionship, and support across various industries. โ€œWe believe that by developing realistic and expressive robot heads, we can bridge the gap between humans and machines, fostering a new era of interactive and intelligent robotics,โ€ said the company in a statement. Reports revealed that to avoid the โ€œuncanny valleyโ€ effect and be able to interact with us, they are given lifelike skin and capabilities to read our emotions and respond appropriately using dynamic expression simulation and emotion generation tech. Bionic skin and high-precision control system The Elf V1 series of humanoids features 30 facial muscles animated by brushless micro-motors and managed by a high-precision control system. Paired with an ability to detect their usersโ€™ emotions with low latency and bionic skin, their facial expressions are nearly identical to those of humans, reported CGTN. The company claims itโ€™s pioneering the development of realistic humanoid robots designed to revolutionize human-robot interaction. Itโ€™s enhancing sophisticated humanoid robot heads that can express emotions, perceive their environment, and interact seamlessly with humans. By combining cutting-edge AI and advanced robotics, AheadForm aims to bring life to machines and transform how humans engage with technology. AI models boost robotsโ€™ responsiveness Seamless integration of Large Language Models (LLMs) and Vision-Language Models (VLMs) into the humanoid robots can help them process and interpret complex data from human interactions, enabling the robot to learn and adapt in real-time, achieving human-level understanding and responsiveness. AheadForm uses Brushless Motors that deliver ultra-quiet operation and high responsiveness, specifically designed for precision facial movements in humanoid robots. With its compact size, lightweight design, and energy efficiency, this motor is the ideal choice for next-generation robots that require precise, subtle facial control to create a truly human-like experience. Previously, the company unveiled the Lan Series that features realistic humanoid robots with soft skin and 10 degrees of freedom, offering a lifelike appearance and intuitive movements. This series is designed for cost-efficiency, for applications prioritizing mobility and manipulation.
1:06

China unveils humanoid robot with lifelike skin and blinking eyes built for daily life | Prabhat Ranjan Mishra, Interesting Engineering Large Language Models (LLMs) and Vision-Language Models (VLMs) help process and interpret complex data from human interactions. A Shanghai-based company has developed humanoid robots that appear as real as humans. The advanced bionic humanoid robot is integrated with self-supervised AI algorithms. Named Elf V1, the robot can perceive the world, communicate, learn, and interact intelligently with its surroundings. Developed by AheadForm Technology, the robot offers up to 30 degrees of freedom, powered by a precise control system and an advanced AI learning algorithm. Robot offers expressive facial features The robot offers expressive facial features, moving eyes, and synchronized speech. It can also convey emotions and understand human non-verbal cues, making interactions more natural and engaging. The robot has highly interactive capabilities and lifelike appearances. AheadForm expects that its robots could soon seamlessly integrate into daily life, providing assistance, companionship, and support across various industries. โ€œWe believe that by developing realistic and expressive robot heads, we can bridge the gap between humans and machines, fostering a new era of interactive and intelligent robotics,โ€ said the company in a statement. Reports revealed that to avoid the โ€œuncanny valleyโ€ effect and be able to interact with us, they are given lifelike skin and capabilities to read our emotions and respond appropriately using dynamic expression simulation and emotion generation tech. Bionic skin and high-precision control system The Elf V1 series of humanoids features 30 facial muscles animated by brushless micro-motors and managed by a high-precision control system. Paired with an ability to detect their usersโ€™ emotions with low latency and bionic skin, their facial expressions are nearly identical to those of humans, reported CGTN. The company claims itโ€™s pioneering the development of realistic humanoid robots designed to revolutionize human-robot interaction. Itโ€™s enhancing sophisticated humanoid robot heads that can express emotions, perceive their environment, and interact seamlessly with humans. By combining cutting-edge AI and advanced robotics, AheadForm aims to bring life to machines and transform how humans engage with technology. AI models boost robotsโ€™ responsiveness Seamless integration of Large Language Models (LLMs) and Vision-Language Models (VLMs) into the humanoid robots can help them process and interpret complex data from human interactions, enabling the robot to learn and adapt in real-time, achieving human-level understanding and responsiveness. AheadForm uses Brushless Motors that deliver ultra-quiet operation and high responsiveness, specifically designed for precision facial movements in humanoid robots. With its compact size, lightweight design, and energy efficiency, this motor is the ideal choice for next-generation robots that require precise, subtle facial control to create a truly human-like experience. Previously, the company unveiled the Lan Series that features realistic humanoid robots with soft skin and 10 degrees of freedom, offering a lifelike appearance and intuitive movements. This series is designed for cost-efficiency, for applications prioritizing mobility and manipulation.

Owen Gregorian

179,005 views โ€ข 9 months ago

Physical AI hits production speed on automotive assembly! ๐Ÿ‘€ Sanctuary AI just achieved 99,5%+ success on a wire plugging task at a Tier 1 automotive supplier, 2.54 seconds per task, validated against live production benchmarks. The system matched the customer's actual production line throughput. The task sounds simple. But if you look closer, it's not. Inserting flexible wires into moving targets on a conveyor requires contact-rich dexterity, force sensing, real-time adaptation. Materials shift. Targets move. This has stayed out of reach for traditional automation. Instead of waiting for humanoid hardware to mature, Sanctuary AI is deploying Physical AI on existing commercial robotic platforms (Universal Robots in this case). So their solution is fully hardware-agnostic. Deploy today on what you already have. Scale to next-gen humanoids later. Olivia Norton (co-founder, CTO): "Physical AI adoption is gated by AI that meets both performance and cycle time requirements. That's what customers are seeking, and that's what we are delivering." Looks like manufacturing, logistics, and other labor-constrained industries don't need to wait. Read more here: ~~ โ™ป๏ธ Join the weekly robotics newsletter, and never miss any news โ†’
0:41

Physical AI hits production speed on automotive assembly! ๐Ÿ‘€ Sanctuary AI just achieved 99,5%+ success on a wire plugging task at a Tier 1 automotive supplier, 2.54 seconds per task, validated against live production benchmarks. The system matched the customer's actual production line throughput. The task sounds simple. But if you look closer, it's not. Inserting flexible wires into moving targets on a conveyor requires contact-rich dexterity, force sensing, real-time adaptation. Materials shift. Targets move. This has stayed out of reach for traditional automation. Instead of waiting for humanoid hardware to mature, Sanctuary AI is deploying Physical AI on existing commercial robotic platforms (Universal Robots in this case). So their solution is fully hardware-agnostic. Deploy today on what you already have. Scale to next-gen humanoids later. Olivia Norton (co-founder, CTO): "Physical AI adoption is gated by AI that meets both performance and cycle time requirements. That's what customers are seeking, and that's what we are delivering." Looks like manufacturing, logistics, and other labor-constrained industries don't need to wait. Read more here: ~~ โ™ป๏ธ Join the weekly robotics newsletter, and never miss any news โ†’

Lukas Ziegler

45,757 views โ€ข 1 month ago

Another awesome robotics company raised funds in Europe. ๐Ÿ‡ช๐Ÿ‡บ This time a company that is shipping robots that build! Monumental has raised $32M Series B led by Khosla Ventures, and its fleet of autonomous bricklaying robots has already built more than 100 real structures across Europe. Houses. A school. A community centre. A hotel. Canal walls. Founded by Salar al Khafaji al Khafaji and Sebastiaan Visser, the co-founders of data visualisation firm Silk, acquired by Palantir in 2016, this is a team that knows how to build and sell a company. The technology is serious: โ†’ Fleet of 100+ electric autonomous robots operating on live job sites today โ†’ Advanced sensors, computer vision and small cranes laying brick to millimetre precision โ†’ All driven by Atrium, their proprietary AI software platform โ†’ Nearly half of all homes built in the last three months alone, pace is compounding fast The business model is also worth taking a look at. Contractors don't buy the robots. They hire Monumental as an autonomous subcontractor and pay for finished wall. So in the end you only pay for the output. This is the same forward-deployed engineering model Palantir pioneered in software. Monumental brought it to physical robotics years before anyone else in the industry caught on. The backdrop makes this urgent. US construction is short 200,000-400,000 workers every month. Since 1945, US manufacturing productivity rose eightfold. Construction gained just 10%, and has actually declined since the 1960s. LET'S MAKE CONSTRUCTION BUSINESSES SEXY AGAIN! ๐Ÿงฑ ~~ โ™ป๏ธ Join the weekly robotics newsletter, and never miss any news โ†’
0:28

Another awesome robotics company raised funds in Europe. ๐Ÿ‡ช๐Ÿ‡บ This time a company that is shipping robots that build! Monumental has raised $32M Series B led by Khosla Ventures, and its fleet of autonomous bricklaying robots has already built more than 100 real structures across Europe. Houses. A school. A community centre. A hotel. Canal walls. Founded by Salar al Khafaji al Khafaji and Sebastiaan Visser, the co-founders of data visualisation firm Silk, acquired by Palantir in 2016, this is a team that knows how to build and sell a company. The technology is serious: โ†’ Fleet of 100+ electric autonomous robots operating on live job sites today โ†’ Advanced sensors, computer vision and small cranes laying brick to millimetre precision โ†’ All driven by Atrium, their proprietary AI software platform โ†’ Nearly half of all homes built in the last three months alone, pace is compounding fast The business model is also worth taking a look at. Contractors don't buy the robots. They hire Monumental as an autonomous subcontractor and pay for finished wall. So in the end you only pay for the output. This is the same forward-deployed engineering model Palantir pioneered in software. Monumental brought it to physical robotics years before anyone else in the industry caught on. The backdrop makes this urgent. US construction is short 200,000-400,000 workers every month. Since 1945, US manufacturing productivity rose eightfold. Construction gained just 10%, and has actually declined since the 1960s. LET'S MAKE CONSTRUCTION BUSINESSES SEXY AGAIN! ๐Ÿงฑ ~~ โ™ป๏ธ Join the weekly robotics newsletter, and never miss any news โ†’

Lukas Ziegler

74,434 views โ€ข 23 days ago

This is the opinion of someone who understands the situation well and how the war in Ukraine is likely to develop - Mariia Berlinska, the head of the Aerial Reconnaissance Support Center. Russia will intensify its aerial terror. We need to prepare for this, and we have almost no time. The Russians will definitely increase the warhead weight of the Shahed drones. It will be increased to several hundred kilograms in order to terrorize cities located at a distance of, say, 30-50-100 kilometers from the front line. Soon we will see autonomous robots. These are even more dangerous than Shaheds. These are systems that are not controlled by humans and will be invulnerable to classic means of electronic warfare or, for example, taking out crews. Right now, the question is not if but when the Russians start manufacturing thousands of them. Imagine the psychological state of people when they go out somewhere on the street in the city and hundreds of Russian drones are circling above the squares and streets, which at any moment can drop something, crash into something, and so on. Watch the video from the post below. There is also good news. It is still possible to prepare for this. It is necessary to deploy comprehensive air defense systems now, including automatic turrets, interceptor drones, and, in the long term, laser weapons, certain samples of electromagnetic weapons, and certain groups that would shoot down targets using various means, as well as certain nets over certain objects. There will be no apocalypse if we prepare ourselves. โ€ผ๏ธ For its own security, it is very important for Europe to be part of this modern defense system and to gain this experience. I hope everyone remembers the Russian reconnaissance drones flying over European countries. Unfortunately, this is only the beginning if we do not counteract them.
2:43

This is the opinion of someone who understands the situation well and how the war in Ukraine is likely to develop - Mariia Berlinska, the head of the Aerial Reconnaissance Support Center. Russia will intensify its aerial terror. We need to prepare for this, and we have almost no time. The Russians will definitely increase the warhead weight of the Shahed drones. It will be increased to several hundred kilograms in order to terrorize cities located at a distance of, say, 30-50-100 kilometers from the front line. Soon we will see autonomous robots. These are even more dangerous than Shaheds. These are systems that are not controlled by humans and will be invulnerable to classic means of electronic warfare or, for example, taking out crews. Right now, the question is not if but when the Russians start manufacturing thousands of them. Imagine the psychological state of people when they go out somewhere on the street in the city and hundreds of Russian drones are circling above the squares and streets, which at any moment can drop something, crash into something, and so on. Watch the video from the post below. There is also good news. It is still possible to prepare for this. It is necessary to deploy comprehensive air defense systems now, including automatic turrets, interceptor drones, and, in the long term, laser weapons, certain samples of electromagnetic weapons, and certain groups that would shoot down targets using various means, as well as certain nets over certain objects. There will be no apocalypse if we prepare ourselves. โ€ผ๏ธ For its own security, it is very important for Europe to be part of this modern defense system and to gain this experience. I hope everyone remembers the Russian reconnaissance drones flying over European countries. Unfortunately, this is only the beginning if we do not counteract them.

Anton Gerashchenko

40,025 views โ€ข 1 year ago

Open-source magnetic tactile sensor for $5! ๐Ÿงฒ Researchers introduced a magnetic tactile sensor that's low-cost, and easy to fabricate, democratizing tactile sensing for robotics. Operating in unstructured environments like homes and offices requires robots to sense forces during physical interaction. Yet the lack of a versatile, accessible tactile sensor has led to fragmented solutions and often force-unaware, sensorless approaches. Building an eFlesh sensor requires four components: a hobbyist 3D printer, off-the-shelf magnets (less than $5), a CAD model, and a magnetometer circuit board. The sensor is 3D printed with magnets embedded in the middle layer. Based on chosen mechanical properties, magnets displace in response to contact forces, measured by a magnetometer underneath. An open-source design tool converts simple OBJ/STL files into 3D-printable STLs. This enables application-specific sensors for robot hands, grippers, quadruped feet, and more. Slip detection generalizes to unseen objects with 95% accuracy. Visual-tactile control policies improve manipulation by 40% over vision-only baselines, achieving 90% success on precise tasks like plug insertion and credit card swiping. All design files, code, trained models, and conversion tools are openly available. Project page: ~~ โ™ป๏ธ Join the weekly robotics newsletter, and never miss any news โ†’
0:57

Open-source magnetic tactile sensor for $5! ๐Ÿงฒ Researchers introduced a magnetic tactile sensor that's low-cost, and easy to fabricate, democratizing tactile sensing for robotics. Operating in unstructured environments like homes and offices requires robots to sense forces during physical interaction. Yet the lack of a versatile, accessible tactile sensor has led to fragmented solutions and often force-unaware, sensorless approaches. Building an eFlesh sensor requires four components: a hobbyist 3D printer, off-the-shelf magnets (less than $5), a CAD model, and a magnetometer circuit board. The sensor is 3D printed with magnets embedded in the middle layer. Based on chosen mechanical properties, magnets displace in response to contact forces, measured by a magnetometer underneath. An open-source design tool converts simple OBJ/STL files into 3D-printable STLs. This enables application-specific sensors for robot hands, grippers, quadruped feet, and more. Slip detection generalizes to unseen objects with 95% accuracy. Visual-tactile control policies improve manipulation by 40% over vision-only baselines, achieving 90% success on precise tasks like plug insertion and credit card swiping. All design files, code, trained models, and conversion tools are openly available. Project page: ~~ โ™ป๏ธ Join the weekly robotics newsletter, and never miss any news โ†’

Lukas Ziegler

289,055 views โ€ข 3 months ago

Robot dogs are now welders! ๐Ÿ‘จ๐Ÿผโ€๐Ÿญ Path Robotics launches a mobile welding robot on quadruped platform, called Rove. This quadruped robotic welding system is paired with their Obsidian physical AI model. Obsidian already delivers autonomous, adaptive welding inside fixed cells. Rove brings intelligent welding to the part rather than moving the part to a fixed workstation. Shipbuilding, heavy construction, and large-scale fabrication share a constraint, massive assemblies and workpieces that cannot be moved or fixtured inside welding cells. These conditions have limited welding automation in environments that need it most, just as skilled welder shortages reach critical levels. Legged robots have long been considered too unstable for precision welding. Rove changes that. Obsidian provides the perception and adaptability needed to operate in high-variability environments. Saronic Technologies, a leader in autonomous maritime vessels, is one of the first early adopters, integrating Rove into its physical AI-powered shipbuilding operations in Franklin, Louisiana. ๐Ÿ‡บ๐Ÿ‡ธ Welding requires millimeter-level precision on a moving quadruped platform, considered impossible until AI-based perception and control made it feasible. ๐Ÿ”ฅ Andrew Lonsberry gotta be honest, but a welding robot dog wasn't on bingo card for 2026. ~~ โ™ป๏ธ Join the weekly robotics newsletter, and never miss any news โ†’
0:44

Robot dogs are now welders! ๐Ÿ‘จ๐Ÿผโ€๐Ÿญ Path Robotics launches a mobile welding robot on quadruped platform, called Rove. This quadruped robotic welding system is paired with their Obsidian physical AI model. Obsidian already delivers autonomous, adaptive welding inside fixed cells. Rove brings intelligent welding to the part rather than moving the part to a fixed workstation. Shipbuilding, heavy construction, and large-scale fabrication share a constraint, massive assemblies and workpieces that cannot be moved or fixtured inside welding cells. These conditions have limited welding automation in environments that need it most, just as skilled welder shortages reach critical levels. Legged robots have long been considered too unstable for precision welding. Rove changes that. Obsidian provides the perception and adaptability needed to operate in high-variability environments. Saronic Technologies, a leader in autonomous maritime vessels, is one of the first early adopters, integrating Rove into its physical AI-powered shipbuilding operations in Franklin, Louisiana. ๐Ÿ‡บ๐Ÿ‡ธ Welding requires millimeter-level precision on a moving quadruped platform, considered impossible until AI-based perception and control made it feasible. ๐Ÿ”ฅ Andrew Lonsberry gotta be honest, but a welding robot dog wasn't on bingo card for 2026. ~~ โ™ป๏ธ Join the weekly robotics newsletter, and never miss any news โ†’

Lukas Ziegler

10,227 views โ€ข 3 months ago